dcmqi-guide
  • Introduction
  • Quick Start
  • Frequently Asked Questions (FAQ)
  • Tutorials
  • Use cases
    • Multi-structure segmentation of the brain
    • Segmentations and measurements from prostate MRI
  • User guide
    • Installation
      • Binary packages
      • Docker images
      • Build from source
      • 3D Slicer extension
    • General principles
    • Coding schemes
      • DICOM-defined coding schemes
      • Searching for codes outside DICOM
      • "Private" coding schemes
    • Command line tools usage
      • Segmentations
        • itkimage2segimage
        • segimage2itkimage
      • Measurements
        • tid1500writer
        • tid1500reader
      • Parametric maps
        • itkimage2paramap
        • paramap2itkimage
  • Developer guide
    • Update Appveyor build dependencies
    • Github release generation
    • Add new attribute to the schema
  • Troubleshooting
  • Limitations
  • Open source credits
Powered by GitBook
On this page
  • segimage2itkimage
  • Usage
  • Examples of DICOM Segmentation objects
Export as PDF
  1. User guide
  2. Command line tools usage
  3. Segmentations

segimage2itkimage

segimage2itkimage

This tool can be used to convert DICOM Segmentation into volumetric segmentations stored as labeled pixels using research format, such as NRRD or NIfTI, and meta information stored in the JSON file format.

Usage

   -t <nrrd|mhd|mha|nii|nifti|hdr|img>,  --outputType <nrrd|mhd|mha|nii
      |nifti|hdr|img>
     Output file format for the resulting image data. (default: nrrd)

   -p <std::string>,  --prefix <std::string>
     Prefix for output file.

   --outputDirectory <std::string>
     Directory to store individual segments saved using the output format
     specified files. When specified, file names will contain prefix,
     followed by the segment number.

   --inputDICOM <std::string>
     File name of the input DICOM Segmentation image object.
     
   --mergeSegments
     Save all segments into a single file. When segments are
     non-overlapping, output is a single 3D file. If overlapping segments
     are identified, multiple 3D files will be created each containing
     non-overlapping segments. Metadata JSON files will be created for each
     such 3D file. (value: 0)

Examples of DICOM Segmentation objects

Here are some representative examples of DICOM Segmentations:

To download the files for the studies listed above:

  1. install idc-index package with pip install --upgrade idc-index

  2. download the study by specifying StudyInstanceUID (listed in the URLs above after the '=' sign) with idc download 1.2.840.113654.2.55.256011367872217445472654886973509892961

Previousitkimage2segimageNextMeasurements

Last updated 9 months ago

If you are looking for publicly available examples of segmentation objects, or other DICOM images, you should check out (IDC) (see documentation ).

Segmentation of a lung nodule from the collection

viewer link:

TotalSegmentator segmentation results from the collection

viewer link:

NCI Imaging Data Commons
here
DICOM-LIDC-IDRI-Nodules
https://viewer.imaging.datacommons.cancer.gov/v3/viewer/?StudyInstanceUIDs=1.3.6.1.4.1.14519.5.2.1.6279.6001.101324598070011890446155612648
TotalSegmentator-CT-Segmentations
https://viewer.imaging.datacommons.cancer.gov/v3/viewer/?StudyInstanceUIDs=1.2.840.113654.2.55.256011367872217445472654886973509892961